An Interactive Chatbot for University Open Day

Abstract

Macau Polytechnic University (MPU) welcomes many visitors on its open day, and it is therefore necessary to provide them with excellent service and guidance. However, there are many difficulties in providing information to visitors, such as the occupation of human resources, language barriers and inaccurate answers, etc. By developing a chatbot to answer the questions from visitors instantly and consistently, helps to save human resources and increase the efficiency of work. An intelligent chatbot can not only provide accurate and appropriate responses but also bring a great communication experience to the visitors. This research uses Natural Language Processing (NLP) and Deep Learning (DL) techniques to develop a chatbot that can engage in interactive conversations with visitors for the MPU open day. A high-performance neural network is built to learn from the given dataset and can accurately answer questions about the MPU open day. Besides, STT (Speech-to-Text) and TTS (Text-to-Speech) APIs are used in this work to assist the communication between computers and humans. This work can be used as a reference framework of fast implementation of a chatbot for any knowledge area with an easy-to-adapt web interface.